{ "@context": "https://schema.org", "@id": "https://aggr.aymericbeaumet.com/items/philschmid-de/2026-08-31-setup-openclaw-2-0-with-gemini-in-under-60-seconds/#webpage", "@type": [ "WebPage", "ArchiveComponent" ], "articleBody": "Five commands, zero fluff: install OpenClaw 2.0 (`v2026.8.1`), link [Gemini 3.8 Flash](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/), our fastest (up to [+300 token/sec](https://artificialanalysis.ai/#speed)) agentic model for coding and agents, and start chatting with live Google search grounding in under a minute.\n\n## What is OpenClaw 2.0?\n\n[OpenClaw](https://openclaw.ai) is a personal AI assistant that actually does things. It runs on your devices, in your chats, with your rules.\n\n- **Chat from anywhere:** Chat from the browser Control UI, Telegram, Discord, WhatsApp, or Slack.\n- **Integrated tooling:** Browser automation, terminal execution, filesystem access, and web search grounding.\n- **Remember:** Keeps memory across sessions so it knows your preferences, projects, and people.\n\n[OpenClaw 2.0](https://openclaw.ai/blog/openclaw-2-accidentally) (`v2026.8.1`) is the largest update yet: simpler install, a rebuilt browser app that opens straight into a conversation, and setup you can finish by talking to your Claw. Full notes: [v2026.8.1](https://docs.openclaw.ai/releases/2026.8.1).\n\n## Prerequisites\n\n- **Node.js:** `Node 26` (recommended) or `Node 22.22.3+` / `24.15+` (`node --version`).\n- **Gemini API Key:** Grab a free key from [Google AI Studio](https://aistudio.google.com/apikey).\n\n## 1\\. Install OpenClaw 2.0\n\nInstall OpenClaw globally via npm:\n\nBash\n\n```bash\nnpm install -g openclaw@2026.8.1\n```\n\nVerify your installation:\n\nBash\n\n```bash\nopenclaw --version\n# Output: OpenClaw 2026.8.1 (ea80657)\n```\n\n## 2\\. Configure Gemini Authentication\n\nExport your Gemini API key in your current shell:\n\nBash\n\n```bash\nexport GEMINI_API_KEY=\"your-gemini-api-key-here\"\n```\n\nTo persist it into OpenClaw's local profile store:\n\nBash\n\n```bash\nopenclaw onboard --non-interactive --accept-risk --skip-health \\\n --mode local \\\n --auth-choice gemini-api-key \\\n --gemini-api-key \"$GEMINI_API_KEY\"\n```\n\n*(Note: You can safely ignore any onboarding tip about configuring a Brave API key—Gemini's built-in Google Search grounding is used automatically.)*\n\n## 3\\. Set Gemini 3.8 Flash as Default\n\nSet **Gemini 3.8 Flash** as the default agent model:\n\nBash\n\n```bash\nopenclaw models set google/gemini-3.8-flash\n```\n\n*(Note: If OpenClaw displays a warning that the model is not in the local catalog, it is safe to ignore. The model is dynamically resolved and validated against Google AI Studio in the next step.)*\n\nVerify model discovery and authentication status:\n\nBash\n\n```bash\nopenclaw models list --provider google\n```\n\n## 4\\. Test Inference via CLI\n\nRun a standalone agent turn in your terminal:\n\nBash\n\n```bash\nopenclaw agent --local --agent main --message \"Hello! What model are you running?\"\n```\n\nOutput:\n\n```text\nI am currently running on google/gemini-3.8-flash.\nWhat would you like to call me?\n```\n\n![OpenClaw CLI Setup](https://www.philschmid.de/static/blog/openclaw-v2-gemini/cli-setup.png)\n\n## 5\\. Start the Gateway & Launch Control UI\n\nSet the gateway to local mode and start it:\n\nBash\n\n```bash\nopenclaw config set gateway.mode local\nopenclaw gateway run\n```\n\n*(To run as a persistent background daemon instead: `openclaw gateway install && openclaw gateway start`. To stop it: `openclaw gateway stop --force`)*\n\nOpen the Control UI in your browser:\n\nBash\n\n```bash\nopenclaw dashboard\n```\n\nThe browser will open to `http://127.0.0.1:18789/` authenticated with your local session token:\n\n![OpenClaw Control UI with Gemini 3.8 Flash](https://www.philschmid.de/static/blog/openclaw-v2-gemini/openclaw-control-ui.png)\n\n## Next Steps\n\n### Google Search Grounding (Enabled by Default)\n\nGoogle Search grounding is **enabled by default** when `GEMINI_API_KEY` is present. No extra configuration or search keys are required.\n\n- Test it directly via CLI:\n\n Bash\n\n ```bash\n openclaw capability web search --query \"Latest gemini models\"\n ```\n\n- In chat sessions, Gemini autonomously runs web searches with citations whenever fresh context is needed.\n\n![Google Search Grounding in OpenClaw Control UI](https://www.philschmid.de/static/blog/openclaw-v2-gemini/openclaw-websearch.png)\n\n- See: [Google Search Grounding in OpenClaw](https://docs.openclaw.ai/tools/gemini-search)\n\n### Leveraging Other Gemini Capabilities\n\n- **[Image Generation](https://docs.openclaw.ai/tools/image-generation):** Set Google's image model using `openclaw models set-image google/gemini-3.1-flash-image`.\n- **[Video Generation](https://docs.openclaw.ai/tools/video-generation):** Generate 4–8s videos with `google/veo-3.1-fast-generate-preview`.\n- **[Music Generation](https://docs.openclaw.ai/tools/music-generation):** Prompt-driven music via `google/lyria-3-clip-preview`.\n- **[Text-to-Speech](https://docs.openclaw.ai/providers/google#text-to-speech):** Gemini batch TTS with natural language style prompting (`gemini-3.1-flash-tts-preview`).\n- **[Realtime Voice](https://docs.openclaw.ai/providers/google#realtime-voice):** Low-latency bidirectional voice streams via Gemini Live API (`gemini-3.1-flash-live-preview`).\n\nFull [Google Documentation](https://docs.openclaw.ai/providers/google).\n\n### Connecting Chat Channels\n\nConnect your Gemini assistant to your favorite messaging apps using simple CLI commands:\n\n- **Browse all channels:** `openclaw channels list --all`\n- **Interactive setup:** `openclaw channels add`\n- **Telegram:** `openclaw channels add --channel telegram --token \"\"`\n- **WhatsApp (QR code):** `openclaw channels login --channel whatsapp`\n- **Discord:** `openclaw channels add --channel discord --token \"\"`\n- **Verify channel status:** `openclaw channels status --probe`\n\nFull [Chat Channels Documentation](https://docs.openclaw.ai/channels).\n", "authors": [], "captured_at": "2026-09-27T19:29:15.293681927+00:00", "category": "programming", "content_html": "

Five commands, zero fluff: install OpenClaw 2.0 (v2026.8.1), link Gemini 3.8 Flash, our fastest (up to +300 token/sec) agentic model for coding and agents, and start chatting with live Google search grounding in under a minute.

\n

What is OpenClaw 2.0?

\n

OpenClaw is a personal AI assistant that actually does things. It runs on your devices, in your chats, with your rules.

\n\n

OpenClaw 2.0 (v2026.8.1) is the largest update yet: simpler install, a rebuilt browser app that opens straight into a conversation, and setup you can finish by talking to your Claw. Full notes: v2026.8.1.

\n

Prerequisites

\n\n

1. Install OpenClaw 2.0

\n

Install OpenClaw globally via npm:

\n

Bash

\n
npm install -g openclaw@2026.8.1\n
\n

Verify your installation:

\n

Bash

\n
openclaw --version\n# Output: OpenClaw 2026.8.1 (ea80657)\n
\n

2. Configure Gemini Authentication

\n

Export your Gemini API key in your current shell:

\n

Bash

\n
export GEMINI_API_KEY="your-gemini-api-key-here"\n
\n

To persist it into OpenClaw's local profile store:

\n

Bash

\n
openclaw onboard --non-interactive --accept-risk --skip-health \\\n  --mode local \\\n  --auth-choice gemini-api-key \\\n  --gemini-api-key "$GEMINI_API_KEY"\n
\n

(Note: You can safely ignore any onboarding tip about configuring a Brave API key—Gemini's built-in Google Search grounding is used automatically.)

\n

3. Set Gemini 3.8 Flash as Default

\n

Set Gemini 3.8 Flash as the default agent model:

\n

Bash

\n
openclaw models set google/gemini-3.8-flash\n
\n

(Note: If OpenClaw displays a warning that the model is not in the local catalog, it is safe to ignore. The model is dynamically resolved and validated against Google AI Studio in the next step.)

\n

Verify model discovery and authentication status:

\n

Bash

\n
openclaw models list --provider google\n
\n

4. Test Inference via CLI

\n

Run a standalone agent turn in your terminal:

\n

Bash

\n
openclaw agent --local --agent main --message "Hello! What model are you running?"\n
\n

Output:

\n
I am currently running on google/gemini-3.8-flash.\nWhat would you like to call me?\n
\n

\"OpenClaw

\n

5. Start the Gateway & Launch Control UI

\n

Set the gateway to local mode and start it:

\n

Bash

\n
openclaw config set gateway.mode local\nopenclaw gateway run\n
\n

(To run as a persistent background daemon instead: openclaw gateway install && openclaw gateway start. To stop it: openclaw gateway stop --force)

\n

Open the Control UI in your browser:

\n

Bash

\n
openclaw dashboard\n
\n

The browser will open to http://127.0.0.1:18789/ authenticated with your local session token:

\n

\"OpenClaw

\n

Next Steps

\n

Google Search Grounding (Enabled by Default)

\n

Google Search grounding is enabled by default when GEMINI_API_KEY is present. No extra configuration or search keys are required.

\n\n

\"Google

\n\n

Leveraging Other Gemini Capabilities

\n\n

Full Google Documentation.

\n

Connecting Chat Channels

\n

Connect your Gemini assistant to your favorite messaging apps using simple CLI commands:

\n\n

Full Chat Channels Documentation.

\n", "content_markdown": "Five commands, zero fluff: install OpenClaw 2.0 (`v2026.8.1`), link [Gemini 3.8 Flash](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/), our fastest (up to [+300 token/sec](https://artificialanalysis.ai/#speed)) agentic model for coding and agents, and start chatting with live Google search grounding in under a minute.\n\n## What is OpenClaw 2.0?\n\n[OpenClaw](https://openclaw.ai) is a personal AI assistant that actually does things. It runs on your devices, in your chats, with your rules.\n\n- **Chat from anywhere:** Chat from the browser Control UI, Telegram, Discord, WhatsApp, or Slack.\n- **Integrated tooling:** Browser automation, terminal execution, filesystem access, and web search grounding.\n- **Remember:** Keeps memory across sessions so it knows your preferences, projects, and people.\n\n[OpenClaw 2.0](https://openclaw.ai/blog/openclaw-2-accidentally) (`v2026.8.1`) is the largest update yet: simpler install, a rebuilt browser app that opens straight into a conversation, and setup you can finish by talking to your Claw. Full notes: [v2026.8.1](https://docs.openclaw.ai/releases/2026.8.1).\n\n## Prerequisites\n\n- **Node.js:** `Node 26` (recommended) or `Node 22.22.3+` / `24.15+` (`node --version`).\n- **Gemini API Key:** Grab a free key from [Google AI Studio](https://aistudio.google.com/apikey).\n\n## 1\\. Install OpenClaw 2.0\n\nInstall OpenClaw globally via npm:\n\nBash\n\n```bash\nnpm install -g openclaw@2026.8.1\n```\n\nVerify your installation:\n\nBash\n\n```bash\nopenclaw --version\n# Output: OpenClaw 2026.8.1 (ea80657)\n```\n\n## 2\\. Configure Gemini Authentication\n\nExport your Gemini API key in your current shell:\n\nBash\n\n```bash\nexport GEMINI_API_KEY=\"your-gemini-api-key-here\"\n```\n\nTo persist it into OpenClaw's local profile store:\n\nBash\n\n```bash\nopenclaw onboard --non-interactive --accept-risk --skip-health \\\n --mode local \\\n --auth-choice gemini-api-key \\\n --gemini-api-key \"$GEMINI_API_KEY\"\n```\n\n*(Note: You can safely ignore any onboarding tip about configuring a Brave API key—Gemini's built-in Google Search grounding is used automatically.)*\n\n## 3\\. Set Gemini 3.8 Flash as Default\n\nSet **Gemini 3.8 Flash** as the default agent model:\n\nBash\n\n```bash\nopenclaw models set google/gemini-3.8-flash\n```\n\n*(Note: If OpenClaw displays a warning that the model is not in the local catalog, it is safe to ignore. The model is dynamically resolved and validated against Google AI Studio in the next step.)*\n\nVerify model discovery and authentication status:\n\nBash\n\n```bash\nopenclaw models list --provider google\n```\n\n## 4\\. Test Inference via CLI\n\nRun a standalone agent turn in your terminal:\n\nBash\n\n```bash\nopenclaw agent --local --agent main --message \"Hello! What model are you running?\"\n```\n\nOutput:\n\n```text\nI am currently running on google/gemini-3.8-flash.\nWhat would you like to call me?\n```\n\n![OpenClaw CLI Setup](https://www.philschmid.de/static/blog/openclaw-v2-gemini/cli-setup.png)\n\n## 5\\. Start the Gateway & Launch Control UI\n\nSet the gateway to local mode and start it:\n\nBash\n\n```bash\nopenclaw config set gateway.mode local\nopenclaw gateway run\n```\n\n*(To run as a persistent background daemon instead: `openclaw gateway install && openclaw gateway start`. To stop it: `openclaw gateway stop --force`)*\n\nOpen the Control UI in your browser:\n\nBash\n\n```bash\nopenclaw dashboard\n```\n\nThe browser will open to `http://127.0.0.1:18789/` authenticated with your local session token:\n\n![OpenClaw Control UI with Gemini 3.8 Flash](https://www.philschmid.de/static/blog/openclaw-v2-gemini/openclaw-control-ui.png)\n\n## Next Steps\n\n### Google Search Grounding (Enabled by Default)\n\nGoogle Search grounding is **enabled by default** when `GEMINI_API_KEY` is present. No extra configuration or search keys are required.\n\n- Test it directly via CLI:\n\n Bash\n\n ```bash\n openclaw capability web search --query \"Latest gemini models\"\n ```\n\n- In chat sessions, Gemini autonomously runs web searches with citations whenever fresh context is needed.\n\n![Google Search Grounding in OpenClaw Control UI](https://www.philschmid.de/static/blog/openclaw-v2-gemini/openclaw-websearch.png)\n\n- See: [Google Search Grounding in OpenClaw](https://docs.openclaw.ai/tools/gemini-search)\n\n### Leveraging Other Gemini Capabilities\n\n- **[Image Generation](https://docs.openclaw.ai/tools/image-generation):** Set Google's image model using `openclaw models set-image google/gemini-3.1-flash-image`.\n- **[Video Generation](https://docs.openclaw.ai/tools/video-generation):** Generate 4–8s videos with `google/veo-3.1-fast-generate-preview`.\n- **[Music Generation](https://docs.openclaw.ai/tools/music-generation):** Prompt-driven music via `google/lyria-3-clip-preview`.\n- **[Text-to-Speech](https://docs.openclaw.ai/providers/google#text-to-speech):** Gemini batch TTS with natural language style prompting (`gemini-3.1-flash-tts-preview`).\n- **[Realtime Voice](https://docs.openclaw.ai/providers/google#realtime-voice):** Low-latency bidirectional voice streams via Gemini Live API (`gemini-3.1-flash-live-preview`).\n\nFull [Google Documentation](https://docs.openclaw.ai/providers/google).\n\n### Connecting Chat Channels\n\nConnect your Gemini assistant to your favorite messaging apps using simple CLI commands:\n\n- **Browse all channels:** `openclaw channels list --all`\n- **Interactive setup:** `openclaw channels add`\n- **Telegram:** `openclaw channels add --channel telegram --token \"\"`\n- **WhatsApp (QR code):** `openclaw channels login --channel whatsapp`\n- **Discord:** `openclaw channels add --channel discord --token \"\"`\n- **Verify channel status:** `openclaw channels status --probe`\n\nFull [Chat Channels Documentation](https://docs.openclaw.ai/channels).\n", "dateCreated": "2026-09-27T19:29:15.293681927+00:00", "date_created": "2026-08-31T00:00:00+00:00", "date_modified": "2026-08-31T00:00:00+00:00", "date_published": "2026-08-31T00:00:00+00:00", "description": "Five commands, zero fluff: install OpenClaw 2.0, connect Gemini 3.8 Flash, and start chatting with live Google Search grounding from your terminal and web dashboard in under a minute.", "external_url": "https://www.philschmid.de/openclaw-v2-gemini", "git": { "commit": "ebb0941c5c06a2ab2377342d607535262a3e969e", "path": "items/philschmid-de/2026/08/2026-08-31-setup-openclaw-2-0-with-gemini-in-under-60-seconds.md", "permalink": "https://github.com/aymericbeaumet/aggr-instance/blob/ebb0941c5c06a2ab2377342d607535262a3e969e/items/philschmid-de/2026/08/2026-08-31-setup-openclaw-2-0-with-gemini-in-under-60-seconds.md" }, "id": "urn:aggr:item:0c3a3436a573d42e03574d8c01339ee60b78f2c5", "isBasedOn": { "@id": "https://www.philschmid.de/openclaw-v2-gemini" }, "mainEntity": { "@id": "https://www.philschmid.de/openclaw-v2-gemini", "@type": "CreativeWork", "archivedAt": { "@id": "https://aggr.aymericbeaumet.com/items/philschmid-de/2026-08-31-setup-openclaw-2-0-with-gemini-in-under-60-seconds/#webpage" }, "dateModified": "2026-08-31T00:00:00+00:00", "datePublished": "2026-08-31T00:00:00+00:00", "headline": "Setup OpenClaw 2.0 with Gemini in Under 60 Seconds", "timeRequired": "PT3M", "url": "https://www.philschmid.de/openclaw-v2-gemini", "wordCount": 641 }, "name": "Archived snapshot: Setup OpenClaw 2.0 with Gemini in Under 60 Seconds", "preview": null, "reading_minutes": 3, "replicated_at": null, "source": "philschmid-de", "source_name": "philschmid.de - RSS feed", "summary": "Five commands, zero fluff: install OpenClaw 2.0, connect Gemini 3.8 Flash, and start chatting with live Google Search grounding from your terminal and web dashboard in under a minute.", "tags": [], "temporalCoverage": "2026-09-27T19:29:15.293681927+00:00", "title": "Setup OpenClaw 2.0 with Gemini in Under 60 Seconds", "url": "https://aggr.aymericbeaumet.com/items/philschmid-de/2026-08-31-setup-openclaw-2-0-with-gemini-in-under-60-seconds/", "word_count": 641 }